Combining cross-modal knowledge transfer and semi-supervised learning for speech emotion recognition.
Sheng ZhangMin ChenJincai ChenYuan-Fang LiYiling WuMinglei LiChuanbo ZhuPublished in: Knowl. Based Syst. (2021)
Keyphrases
- semi supervised learning
- knowledge transfer
- cross modal
- transfer learning
- speech emotion recognition
- labeled data
- multi modal
- semi supervised
- unlabeled data
- learning tasks
- cross domain
- knowledge sharing
- supervised learning
- active learning
- unsupervised learning
- text categorization
- training data
- text classification
- recommender systems
- data sets
- visual data
- multi label classification
- image retrieval
- feature vectors
- pairwise
- feature extraction